{"id":20436433,"url":"https://github.com/galmetzer/self-sample","last_synced_at":"2025-04-12T21:42:18.712Z","repository":{"id":39923053,"uuid":"373215998","full_name":"galmetzer/self-sample","owner":"galmetzer","description":"Single shape Deep Point Cloud Consolidation [TOG 2021]","archived":false,"fork":false,"pushed_at":"2022-05-21T07:04:57.000Z","size":29707,"stargazers_count":45,"open_issues_count":0,"forks_count":8,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-12T21:42:08.204Z","etag":null,"topics":["deep-learning","point-cloud","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/galmetzer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-06-02T15:25:21.000Z","updated_at":"2025-04-09T12:01:05.000Z","dependencies_parsed_at":"2022-09-15T12:10:28.678Z","dependency_job_id":null,"html_url":"https://github.com/galmetzer/self-sample","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/galmetzer%2Fself-sample","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/galmetzer%2Fself-sample/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/galmetzer%2Fself-sample/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/galmetzer%2Fself-sample/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/galmetzer","download_url":"https://codeload.github.com/galmetzer/self-sample/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248637833,"owners_count":21137538,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","point-cloud","pytorch"],"created_at":"2024-11-15T08:41:32.133Z","updated_at":"2025-04-12T21:42:18.685Z","avatar_url":"https://github.com/galmetzer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Self-Sampling - for neural point cloud consolidation\n\u003cimg src='docs/images/lamp-teaser.jpg' align=\"right\" width=325\u003e\nWe introduce a novel technique for neural point cloud consolidation\nwhich learns from only the input point cloud.\n\n### TOG 2021 [[Paper]](https://arxiv.org/abs/2008.06471) [[Project Page]](https://galmetzer.github.io/self-sample/)\u003cbr\u003e\nby [Gal Metzer](https://galmetzer.github.io/), [Rana Hanocka](https://www.cs.tau.ac.il/~hanocka/), [Raja Giryes](http://web.eng.tau.ac.il/~raja), and [Daniel Cohen-Or](https://danielcohenor.com/)\n\n# Getting Started\n\n### Installation\n- Clone this repo:\n\n#### Setup Conda Environment\n- Relies on [PyTorch](https://pytorch.org/) version 1.7.1 \u003cbr\u003e\n- [Pytorch Geometric](https://github.com/rusty1s/pytorch_geometric) \n- Everything can be installed via conda environment `conda env create -f env.yml` (creates an environment called self-sample)\n  \n# Running Examples\nThe demos folder contains examples from the paper.\u003cbr\u003e\nFor each shape the demo runs the optimization and inference parts. \u003cbr\u003e\nFor instance, to run the lamp demo simply execute from the root project folder: \n```\ndemos/lamp.sh\n```\n\nThe results would be found at `demos-results/lamp/lamp_result.xyz`,\n\u003c/br\u003e\nand respectively for the other shapes as well.\n\n#### Example shapes\n\n- alien, anchor, lamp - sharp point consolidation\n- candle, scanned Leg, tiki - sparse point consolidation\n- camera_noised - denoising \n\n\n# Citation\nIf you find this code useful, please consider citing our paper\n```\n@article{metzer2020self,\nauthor = {Metzer, Gal and Hanocka, Rana and Giryes, Raja and Cohen-Or, Daniel},\ntitle = {Self-Sampling for Neural Point Cloud Consolidation},\nyear = {2021},\nissue_date = {October 2021},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nvolume = {40},\nnumber = {5},\nissn = {0730-0301},\nurl = {https://doi.org/10.1145/3470645},\ndoi = {10.1145/3470645},\n}\n```\n\n# Questions / Issues\nIf you have questions or issues running this code, please open an issue.\n\nNote: the original implementation used [this implementation](https://github.com/erikwijmans/Pointnet2_PyTorch)\nof PointNet++, which is not guaranteed to supported newer versions of pytorch. \n\u003c/br\u003e\nThis implementation uses [Pytorch Geometric](https://github.com/rusty1s/pytorch_geometric) instead,\nwhich can not hold large subsets at train time.\n\nTherefore, demos are designed for subset sizes lower than used in the paper.\nIncreasing the subset size to 12K-14K on an appropriate GPU, improves the accuracy of the results.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgalmetzer%2Fself-sample","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgalmetzer%2Fself-sample","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgalmetzer%2Fself-sample/lists"}